A tool to discover and catalog Model Context Protocol (MCP) servers from GitHub repositories. This tool automatically searches GitHub for MCP server implementations, analyzes their documentation, and generates standardized registry entries.

• Automated GitHub repository search for MCP servers
• AI-powered analysis of README files
• Registry entry generation for new servers
• Support for multiple file formats (JSON, YAML, Markdown)
• Configurable search patterns and keywords

• Node.js (v14 or higher) and npm
• GitHub Personal Access Token with repo scope
• Azure OpenAI API access (or other compatible OpenAI API provider)

1. Clone the repository:

   git clone https://github.com/yourusername/mcp-server-finder.git
   cd mcp-server-finder

2. Install dependencies:

   npm install

3. Configure environment variables: Create a .env file in the root directory with the following variables:

   GITHUB_TOKEN=your_github_personal_access_token
   AZURE_OPENAI_API_KEY=your_azure_openai_api_key
   AZURE_OPENAI_ENDPOINT=https://your-resource-name.openai.azure.com/
   AZURE_OPENAI_DEPLOYMENT=your_deployment_name
   

1. Run the server finder:

   npm start

2. For custom search parameters:

   npm start -- --keywords="mcp,model context protocol" --max-results=50

3. Export results to a specific format:

   npm start -- --output=json --output-file=mcp-servers.json

You can customize the search behavior by modifying the config.js file:

• searchKeywords: Array of keywords to search for
• excludeKeywords: Array of keywords to exclude from results
• maxResults: Maximum number of repositories to analyze
• outputFormat: Default output format (json, yaml, markdown)
• registryTemplate: Template for registry entries

1. The tool searches GitHub repositories using the GitHub API and specified keywords
2. For each matching repository, it fetches the README and other documentation
3. The content is analyzed using Azure OpenAI to identify MCP server characteristics
4. If a repository is determined to be an MCP server, a registry entry is generated
5. Results are saved in the specified output format

1. Go to GitHub Settings > Developer settings > Personal access tokens
2. Generate a new token with the repo scope
3. Copy the token and add it to your .env file

1. Create an Azure OpenAI resource in the Azure portal
2. Deploy a model in the Azure OpenAI Studio
3. Get your API key, endpoint, and deployment name from the Azure portal
4. Add these credentials to your .env file

Contributions are welcome! Please feel free to submit a Pull Request.

This project is licensed under the MIT License - see the LICENSE file for details.